Image analysis is the science and art of extracting quantitative measurements from, or detecting and recognizing objects in, images. Given that imaging sensors are starting to be built into every phone, car, and other appliances, this is a burgeoning field. Its methods also allow to ask and answer new questions in data-intensive sciences such as large-scale astronomical sky surveys, or in neurobiology.
This lecture will give you insight into ideas, mathematical and algorithmic techniques ranging from low-level concepts such as unitary transforms all the way to highly engineered feature descriptors that are at the heart of modern object recognition pipelines.
This lecture assumes no prior experience in pattern recognition or image analysis.
Example application of image analysis.
Data: W. Denk, K. Briggman, MPI for Medical Research, Heidelberg.
Lecture Videos (Youtube playlist)
- Human early vision
- Image representations
- Block Matching
- Texture Synthesis
- Non-Local Means for Image Denoising
- BM3D for image denoising
- Unitary transformations
- The Fourier Transform
- The Discrete Fourier Transform (DFT)
- 2D-DFT: Application to Images
- Fourier Transform
- Time Frequency Decompositions
- The Wavelet Transform
- Maximally Stable Extremal Regions (MSER)
- Mathematical Morphology
- Minkowski functionals
- Markov Random Fields (MRFs)
- Gaussian Markov Random Fields (GMRF)
- Intrinsic GMRFs (IGMRF)
- Factor Graphs
- Fields of Experts
- Discrete-Valued MRFs
- MAP inference via Integer Linear Programming (ILP)
- Integer Linear Programs (continued)
- Pseudo Boolean Functions (PBFs)
- Quadratic PBFs with submodular terms
- Max-Flow / Min-Cut
- Graph Cuts
- Example model: Tracking by assignment
- Structured Support Vector Machine (structSVM)
- Structured Learning: Applications
- Light Fields
- Coded Aperture Imaging
- Compressive Sensing
2 Patches in Image Analysis
3 Fourier Transformation
5 Images as Topographic Maps
6 Gaussian Random Fields
7 Fields of Experts, Discrete MRFs
8 Binary pairwise MRFs and Graph Cut
9 Structured learning
10 Light Fields and Compressive Sensing
- Lecturer: Prof. Dr. Fred Hamprecht
- TA: Christoph Decker
- Lecture: Tuesday, 14.15-16.00, Wednesday, 14.15-16.00
HCI, Speyerer Strasse 6, large seminar room
- Exercises: Wednesday, 16.15-18.00 (same place as lecture)
- S. J. D. Prince: Computer Vision: Models, Learning, and Inference. Cambridge Univ. Press, 2012
- M. Sonka, V. Hlavac, R. Boyle: Image Processing, Analysis and Machine Vision.
Thomson Learning, 2008.
- B. Jähne: Digital Image Processing.
Last update: 24.04.2015, 12:33